winoground

Dataset Card for Winoground

Dataset Description

Winoground is a novel task and dataset for evaluating the ability of vision and language models to conduct visio-linguistic compositional reasoning. Given two images and two captions, the goal is to match them correctly—but crucially, both captions contain a completely identical set of words/morphemes, only in a different order. The dataset was carefully hand-curated by expert annotators and is labeled with a rich… See the full description on the dataset page: https://huggingface.co/datasets/facebook/winoground.

数据集卡片：Winoground

数据集描述：Winoground是一种新颖的任务和数据集，旨在评估视觉和语言模型在执行视语言组合推理方面的能力。给定两张图像和两组标题，目标在于正确匹配它们——然而，至关重要的是，两组标题均包含完全相同的词汇/语素集合，仅顺序不同。该数据集由专家注释员精心手工编纂，并附有丰富的标签……请参阅数据集页面上的完整描述：https://huggingface.co/datasets/facebook/winoground。